Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.2523. Min Act: -0.1700
Data Index: 2580769 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1898. Min Act: -0.1700
Data Index: 6514308 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1898. Min Act: -0.1700
Data Index: 4642742 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1586. Min Act: -0.1700
Data Index: 359446 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1586. Min Act: -0.1700
Data Index: 4112391 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1586. Min Act: -0.1700
Data Index: 7816994 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1586. Min Act: -0.1700
Data Index: 7408652 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 7598389 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 4615928 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0960. Min Act: -0.1700
Data Index: 3605888 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 1018529 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 3605891 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0648. Min Act: -0.1700
Data Index: 906485 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0335. Min Act: -0.1700
Data Index: 2686549 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0335. Min Act: -0.1700
Data Index: 782828 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0335. Min Act: -0.1700
Data Index: 6178771 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0335. Min Act: -0.1700
Data Index: 1879024 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0335. Min Act: -0.1700
Data Index: 3572987 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0335. Min Act: -0.1700
Data Index: 5735626 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0023. Min Act: -0.1700
Data Index: 2974510 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19